© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15147
    Prev
    Next
    INDEX
    Explanations

    flesh, pulp, and meat

    np_acts-logits-general · gemini-2.5-flash-lite

    biological tissue terms like "flesh", "pulp", "parenchyma", and "cells".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abstractmethod
    -1.38
    ⇿
    -1.34
     in
    -1.30
     on
    -1.29
     člá
    -1.23
    ྜ
    -1.23
     fratello
    -1.22
     It
    -1.21
     Headquarters
    -1.20
     Eigentü
    -1.19
    POSITIVE LOGITS
    tigem
    1.20
     trouverez
    1.18
     travaillent
    1.13
     both
    1.11
     devriez
    1.09
    ⌦
    1.09
     "
    1.08
    ➪
    1.05
    )
    1.05
    zeit
    1.01
    Activations Density 0.078%

    No Known Activations