© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27598
    Prev
    Next
    INDEX
    Explanations

    also followed by action or related item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    ऎ
    0.44
    ই
    0.41
    卋
    0.39
    ение
    0.39
     c
    0.37
    ᴿ
    0.37
    锡
    0.36
    いくつ
    0.35
    は
    0.35
    gen
    0.35
    POSITIVE LOGITS
     BTW
    0.46
     btw
    0.41
     தம்
    0.40
    BTW
    0.40
    }^{+},
    0.38
     Nachhalt
    0.38
    Voices
    0.37
     mee
    0.36
    hte
    0.36
     ইমাম
    0.36
    Activations Density 0.012%

    No Known Activations