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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 28
    Prev
    Next
    INDEX
    Explanations

    always, often, or essentially

    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
     inzwischen
    1.35
    на
    1.15
     następnie
    1.13
    ल
    1.11
     будто
    1.11
    ১২
    1.09
    ১৩
    1.07
    otro
    1.06
    DESTROY
    1.06
     verdadero
    1.06
    POSITIVE LOGITS
    tout
    1.21
    ﺢ
    1.19
    tics
    1.13
    yyyyyyyy
    1.12
    য়ের
    1.10
    yyyy
    1.09
    ই
    1.08
    keiten
    1.07
    ﻤ
    1.07
    ﻐ
    1.06
    Activations Density 1.576%

    No Known Activations