© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5220
    Prev
    Next
    INDEX
    Explanations

    his/her/my voice

    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_29_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
    :
    0.87
     hum
    0.79
    :</
    0.79
    hum
    0.76
    :"))
    0.76
    _:
    0.76
     murmured
    0.73
    זור
    0.72
    :*
    0.69
     sighed
    0.67
    POSITIVE LOGITS
     Trying
    1.06
     keeping
    1.06
     dando
    1.04
     voice
    1.03
     trying
    1.02
    voice
    1.01
     referring
    0.99
     gaining
    0.98
     Keeping
    0.96
     recordando
    0.95
    Activations Density 0.040%

    No Known Activations