© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2059
    Prev
    Next
    INDEX
    Explanations

    asking for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ości
    2.35
    ০
    2.30
    kina
    2.26
     नहीं
    2.20
    iéndose
    2.16
     việc
    2.15
     miệng
    2.14
    이
    2.13
    م
    2.07
    ﻭ
    2.06
    POSITIVE LOGITS
    }:
    1.92
    /*
    1.83
    ש
    1.83
     incentiv
    1.80
    }));
    1.79
     appunto
    1.70
     attenuate
    1.70
    larghezza
    1.69
    affiche
    1.65
    一是
    1.64
    Activations Density 0.380%

    No Known Activations